OpenAI GPT OSS 120B
LiveOpenAI128K context · Text, Tools
Best discount now99.0%offYou pay 1.0% of reference.
Median discount99.0%offAcross 405 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h6,852405 offers from 53 sellers.
Current offers
405 of 600 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$2
∞
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$0.159
∞
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$0.090
∞
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$0.047
∞
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$0.014
∞
Amazon Bedrock
99%
$0.00069 in
$0.00297 out
916ms
99.4%
∞
$0.033
∞
Ollama Cloud ?
99%
$0.00070 in
$0.00300 out
-
-
∞
$0.002
∞
Ollama Cloud ?
99%
$0.00070 in
$0.00300 out
-
-
∞
-
∞
Ollama Cloud ?
99%
$0.00070 in
$0.00300 out
-
-
∞
-
∞
Ollama Cloud ?
99%
$0.00070 in
$0.00300 out
-
-
∞
-
∞
Total
Cumulative offers
Offered
∞
Sold
$3
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
20:105,853 tokensFireworks AI direct99.0%
20:05455 tokensFireworks AI direct98.9%
20:054,738 tokensAWS Bedrock99.0%
20:05706 tokensFireworks AI direct98.8%
20:05544 tokensFireworks AI direct99.1%
20:05712 tokensFireworks AI direct99.4%
20:05644 tokensFireworks AI direct99.3%
20:04520 tokensFireworks AI direct98.9%
Settled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Fireworks AI direct | 1.67 s | 10.11 s | — | 99.7% | 57% |
| AWS Bedrock | 3.04 s | 18.42 s | 329 tok/s | 99.4% | 38% |
| Venice AI direct | 4.11 s | 18.42 s | 54 tok/s | 99.5% | 3% |
| Concentrate.ai | 18.42 s | 150.53 s | — | 97.2% | 2% |
| Mordiem | 1.67 s | — | — | 73.0% | 0% |
Fireworks AI direct57% of traffic
99.7% success
AWS Bedrock38% of traffic
99.4% success
Venice AI direct3% of traffic
99.5% success
Concentrate.ai2% of traffic
97.2% success
Mordiem0% of traffic
73.0% success
Use this modelChange your base URL.
Change your base URL.
Keep your code.
Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.
Read the quickstart ↗curl $SURPLUS_BASE_URL/chat/completions \ -H "Authorization: Bearer $SURPLUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "openai-gpt-oss-120b", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1